In many time-aware item recommender systems, modeling the accurate evolution of both user profiles and the contents of items over time is essential. However, most existing methods focus on learning users' dynamic interests, where the contents of items are assumed to be stable over time. They thus fail to capture the dynamic changes in the item's contents. In this paper, we present a novel method CDUE for time-aware item recommendation, which captures the evolution of both user's interests and item's contents information via topic dynamics. Specifically, we propose a dynamic sparse topic model to track the evolution of topics for changes in items' contents over time and adapt a vector autoregressive model to profile users' dynamic interests. The item's topics and user's interests and their evolutions are learned collaboratively and simultaneously into a unified learning framework. Experimental results on two real-world data sets demonstrate the quality and effectiveness of the proposed method and show that our method can be used to make better future recommendations.

Recommender systems have achieved great success in recent years, and matrix approximation (MA) is one of the most popular techniques for collaborative filtering (CF) based recommendation. However, a major issue is that MA methods perform poorly at detecting strong localized associations among closely related users and items. Recently, some MA-based CF methods adopt clustering methods to discover meaningful user-item subgroups and perform ensemble on different clusterings to improve the recommendation accuracy. However, ensemble learning suffers from lower efficiency due to the increased overall computation overhead. In this paper, we propose GLOMA, a new clustering-based matrix approximation method, which can embed global information in local matrix approximation models to improve recommendation accuracy. In GLOMA, a MA model is first trained on the entire data to capture global information. The global MA model is then utilized to guide the training of cluster-based local MA models, such that the local models can detect strong localized associations shared within clusters and at the same time preserve global associations shared among all users/items. Evaluation results using MovieLens and Netflix datasets demonstrate that, by integrating global information in local models, GLOMA can outperform five state-of-the-art MA-based CF methods in recommendation accuracy while achieving descent efficiency.

In our daily life, short texts have been everywhere especially since the emergence of social network. There are countless short texts in online media like twitter, online Q&A sites and so on. Discovering topics is quite valuable in various application domains such as content recommendation and text characterization. Traditional topic models like LDA are widely applied for sorts of tasks, but when it comes to short text scenario, these models may get stuck due to the lack of words. Recently, a popular model named BTM uses word co-occurrence relationship to solve the sparsity problem and is proved effectively. However, both BTM and extended models ignore the inside relationship between words. From our perspectives, more related words should appear in the same topic. Based on this idea, we propose a model named RIBS-TM which makes use of RNN for relationship learning and IDF for filtering high-frequency words. Experiments on two real-world short text datasets show great utility of our model.

In real world social networks, there are multiple cascades which are rarely independent. They usually compete or cooperate with each other. Motivated by the reinforcement theory in sociology we leverage the fact that adoption of a user to any behavior is modeled by the aggregation of behaviors of its neighbors. We use a multidimensional marked Hawkes process to model users product adoption and consequently spread of cascades in social networks. The resulting inference problem is proved to be convex and is solved in parallel by using the barrier method. The advantage of the proposed model is twofold; it models correlated cascades and also learns the latent diffusion network. Experimental results on synthetic and two real datasets gathered from Twitter, URL shortening and music streaming services, illustrate the superior performance of the proposed model over the alternatives.

Data classification and tag recommendation are both important and challenging tasks in social media. These two tasks are often considered independently and most efforts have been made to tackle them separately. However, labels in data classification and tags in tag recommendation are inherently related. For example, a Youtube video annotated with NCAA, stadium, pac12 is likely to be labeled as football, while a video/image with the class label of coast is likely to be tagged with beach, sea, water and sand. The existence of relations between labels and tags motivates us to jointly perform classification and tag recommendation for social media data in this paper. In particular, we provide a principled way to capture the relations between labels and tags, and propose a novel framework CLARE, which fuses data CLAssification and tag REcommendation into a coherent model. With experiments on three social media datasets, we demonstrate that the proposed framework CLARE achieves superior performance on both tasks compared to the state-of-the-art methods.

Do you think you can tell a piece of music composed by artificial intelligence (AI) from one created by a human composer? Before you read any further, let's find out. The following audio consists of two fragments, one written by AI, the other by a human. TNW Conference won best European Event 2016 for our festival vibe. See what's in store for 2017.

Hoping to go to Google's annual developer conference this spring? If you are, mark your calendar for Feb. 22. That's the day when you can first apply for tickets to Google I/O. Google announced on its events page that the window for submitting ticket applications is between Feb. 22 at 1 p.m. ET and Feb. 27 at 8 p.m. ET. The conference is being held May 17-19 at the Shoreline Amphitheatre in Mountain View, Calif. This is the second year that the event will be held in Mountain View.

TheTake, a site which launched as a way for consumers to buy that thing they saw in that movie, is set to begin selling an automated version of its service directly to businesses. The New York-based company is pitching studios and entertainment sites on a machine learning system that can identify products and locations as a way to generate revenue from product placements and experiential travel based on set locations. The new product is based on a year's worth of work that TheTake's development did to train a proprietary machine learning algorithm to identify images using a different technique than the industry standard, according to TheTake's chief executive Ty Cooper. Initially, the team behind TheTake would manually enter all the datasets and use an off-the-shelf computer visualization tool to identify images that fit the pre-defined parameters set by the company's staff. Companies like Universal Pictures, Comcast, Bravo, E!, Fandango, Sony Pictures and the Hallmark Channel, are testing out the AI-based service now, according to an email from Cooper.

While I am still not sure that Scarlett Johansson is the best person to play the Major in the upcoming live-action Ghost in the Shell movie, the latest trailer confirms my suspicions that it is the film's narrative that could be more of an issue. I've already explained why I think the new changes to this Ghost in the Shell adaptation are problematic in a narrative sense but this latest trailer really emphasizes how far the plot is deviating from the host material. The reason why this is an issue, is that one of the main core aspects to the Major's character is that she is battling with her machine self in order to retain her humanity. It is a core aspect to almost all of Masamune Shirow's cyberpunk related work. In that, do you lose your humanity when part or even most of your body is a machine. You could say that's the whole point of what Ghost in the Shell actually means; that your spirit or "ghost" is trapped within the "shell" of a machine.

One of the greatest features of having a voice-powered speaker in our homes is the ability to play a song when the moment strikes. Google Home has always included support for Spotify, YouTube Music, Pandora, and TuneIn, letting you fill your house with music just by asking, but now it's making its own service a whole lot smarter. Subscribers to Google Play Music can now tap into a new personalized world of music with Google Home. Where you previously had to meticulously create your own playlists for workouts or dinner parties, Google will now let Assistant be your DJ, as the service combines "machine learning and information like weather, activity, and location" to deliver the perfect playlist for whatever you happen to be doing: "Say you're making pizza and your hands are covered in flour. Just say, 'Ok Google, play music for cooking' and we'll serve up the perfect tunes, like our R&B Kitchen Dance Party playlist. If you've had a long day at work and are too tired to move a muscle, say'Ok Google, play music for relaxing' and get a playlist like Mellow Pop without lifting a finger."